Vision-based Perception for Autonomous Vehicles in Obstacle Avoidance Scenarios

TL;DR

This paper presents a camera-only perception and planning system for autonomous vehicles that effectively detects and avoids obstacles in complex environments, validated through real-world campus experiments.

Contribution

It introduces an obstacle avoidance pipeline combining YOLOv11 and monocular depth estimation with a Frenet-Pure Pursuit planner, advancing perception accuracy and efficiency.

Findings

Effective obstacle detection and avoidance demonstrated in campus scenarios

Comparative analysis of depth estimation models highlights accuracy and robustness

System enhances autonomous navigation safety and reliability

Abstract

Obstacle avoidance is essential for ensuring the safety of autonomous vehicles. Accurate perception and motion planning are crucial to enabling vehicles to navigate complex environments while avoiding collisions. In this paper, we propose an efficient obstacle avoidance pipeline that leverages a camera-only perception module and a Frenet-Pure Pursuit-based planning strategy. By integrating advancements in computer vision, the system utilizes YOLOv11 for object detection and state-of-the-art monocular depth estimation models, such as Depth Anything V2, to estimate object distances. A comparative analysis of these models provides valuable insights into their accuracy, efficiency, and robustness in real-world conditions. The system is evaluated in diverse scenarios on a university campus, demonstrating its effectiveness in handling various obstacles and enhancing autonomous navigation. The video presenting the results of the obstacle avoidance experiments is available at: https://www.youtube.com/watch?v=FoXiO5S_tA8